Model comparison
Claude Opus 4.6 vs Kimi K2.5
Claude Opus 4.6 is the stronger model overall, scoring 58.2 to 48.1 on the Noometry Index. Kimi K2.5 costs 11× less per token, which makes it the better buy when Claude Opus 4.6's lead doesn't matter for your workload.
Last verified . 47 shared benchmarks.
Summary
- They share 47 benchmarks with published results for both. Claude Opus 4.6 scores higher in 8 categories and Kimi K2.5 in 2 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Opus 4.6 leads 57.8 to 31.2.
- The biggest single-benchmark swing is ARC-AGI-2: 69.2% for Claude Opus 4.6 and 11.8% for Kimi K2.5.
- Kimi K2.5 is cheaper at $0.45 / $2.25 per million input/output tokens, against $5 / $25 for Claude Opus 4.6.
- Claude Opus 4.6 accepts more context: 1M tokens versus 262K.
- Kimi K2.5 has downloadable open weights; the other is API-only.
Side by side
| Claude Opus 4.6 | Kimi K2.5 | |
|---|---|---|
| Provider | Anthropic | Moonshot AI |
| Noometry Index | 58.2 | 48.1 |
| Released | 2026-02-04 | 2026-01-27 |
| Weights | Proprietary | Open |
| Context window | 1M | 262K |
| Max output | 128K | 262K |
| Input $ / M tokens | $5 | $0.45 |
| Output $ / M tokens | $25 | $2.25 |
| Results tracked | 68 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4.6 leads
Claude Opus 4.6: 57.2 (#20), Kimi K2.5: 48.8 (#53)
| Benchmark | Claude Opus 4.6 | Kimi K2.5 |
|---|---|---|
| SWE-bench Verified | 78.7% | 73.8% |
| SWE-bench Verified (bash only) | 75.6% | 70.8% |
| LMArena WebDev | 1547 | 1437 |
| SWE-bench Multilingual | 72% | 67.3% |
| WeirdML | 78% | 45.6% |
| LMArena Coding | 1536 | 1474 |
| ALE-Bench | 996.5 | 821.65 |
| FrontierCode | 26.6% | — |
| SciCode | — | 49% |
| GSO | 41.2% | — |
| AlgoTune | 1.47 | — |
Agentic & Tool Use Claude Opus 4.6 leads
Claude Opus 4.6: 51.1 (#4), Kimi K2.5: 34.2 (#48)
| Benchmark | Claude Opus 4.6 | Kimi K2.5 |
|---|---|---|
| Terminal-Bench | 79.8% | 43.2% |
| Vending-Bench 2 | 8,018 | 1,198 |
| APEX-Agents | 46.3% | — |
| Remote Labor Index | 4.2% | — |
| τ²-bench Banking | 27.3% | — |
| Cybench | 93% | — |
| DeepResearch Bench | 55.3% | — |
| OSWorld | — | 63.3% |
| GBAEval | 44.1% | — |
| LMArena Search | 1253 | — |
| METR Time Horizons | 78.9% | — |
Reasoning Claude Opus 4.6 leads
Claude Opus 4.6: 57.8 (#23), Kimi K2.5: 31.2 (#80)
| Benchmark | Claude Opus 4.6 | Kimi K2.5 |
|---|---|---|
| ARC-AGI-2 | 69.2% | 11.8% |
| SimpleBench | 67.6% | 46.8% |
| Kagi LLM Benchmark | 83.6% | 78.5% |
| NYT Connections (extended) | 92.1% | 69.9% |
| ARC-AGI-1 | 94% | 65.3% |
| Chess Puzzles | 17% | 12% |
| EnigmaEval | 7.6% | 3.4% |
| Thematic Generalization | 80.6% | 69.4% |
| LMArena Hard Prompts | 1527 | 1453 |
| Epoch Capabilities Index | 155.24 | 148.03 |
| CritPt | — | 3.1% |
| EBR-Bench | 12.7% | — |
| Mystery Game Puzzles | 25% | — |
| DTBench | 91.2% | — |
| LMCA | 55.8% | — |
| ForecastBench | 60 | — |
Math Claude Opus 4.6 leads
Claude Opus 4.6: 63.0 (#31), Kimi K2.5: 51.8 (#53)
| Benchmark | Claude Opus 4.6 | Kimi K2.5 |
|---|---|---|
| MathArena Final-Answer Competitions | 78.5% | 62.3% |
| OTIS Mock AIME 2024-2025 | 94.4% | 92.2% |
| LMArena Math | 1519 | 1470 |
| FrontierMath (Feb 2025 set) | 40.7% | 27.9% |
| FrontierMath Tier 4 (v1) | 22.9% | 4.2% |
| FrontierMath (Tiers 1-3) | 66% | — |
| FrontierMath Tier 4 | 26.8% | — |
| ProofBench | 50% | — |
Knowledge Claude Opus 4.6 leads
Claude Opus 4.6: 61.9 (#26), Kimi K2.5: 53.6 (#56)
| Benchmark | Claude Opus 4.6 | Kimi K2.5 |
|---|---|---|
| GPQA Diamond | 90.5% | 87.6% |
| Humanity's Last Exam | 34.4% | 24.4% |
| SimpleQA Verified | 47% | 34.3% |
| Vectara Hallucination Rate | 12.2% | 14.2% |
| LMArena Expert | 1546 | 1466 |
Multimodal Kimi K2.5 leads
Claude Opus 4.6: 37.3 (#74), Kimi K2.5: 41.1 (#39)
| Benchmark | Claude Opus 4.6 | Kimi K2.5 |
|---|---|---|
| LMArena Vision | 1316 | 1269 |
| LMArena Document | 1507 | 1430 |
| Furniture Assembly | 28.3% | — |
Multilingual Claude Opus 4.6 leads
Claude Opus 4.6: 57.9 (#6), Kimi K2.5: 53.9 (#53)
| Benchmark | Claude Opus 4.6 | Kimi K2.5 |
|---|---|---|
| LMArena Non-English | 1489 | 1433 |
| LMArena Chinese | 1551 | 1495 |
| LMArena French | 1513 | 1454 |
| LMArena German | 1502 | 1441 |
| LMArena Japanese | 1484 | 1421 |
| LMArena Korean | 1464 | 1410 |
| LMArena Russian | 1497 | 1435 |
| LMArena Spanish | 1510 | 1450 |
Instruction Following Claude Opus 4.6 leads
Claude Opus 4.6: 79.5 (#4), Kimi K2.5: 75.3 (#64)
| Benchmark | Claude Opus 4.6 | Kimi K2.5 |
|---|---|---|
| LMArena Instruction Following | 1523 | 1431 |
Long Context Kimi K2.5 leads
Claude Opus 4.6: 48.1 (#13), Kimi K2.5: 52.1 (#7)
| Benchmark | Claude Opus 4.6 | Kimi K2.5 |
|---|---|---|
| CL-bench | 20.7% | 19.3% |
| CL-bench Life | 17% | 13.2% |
| LMArena Longer Query | 1520 | 1445 |
| Fiction.LiveBench | — | 86.1% |
Writing & Preference Claude Opus 4.6 leads
Claude Opus 4.6: 73.5 (#10), Kimi K2.5: 65.1 (#53)
| Benchmark | Claude Opus 4.6 | Kimi K2.5 |
|---|---|---|
| LMArena Text | 1503 | 1445 |
| LMArena Creative Writing | 1505 | 1423 |
| EQ-Bench Creative Writing | 1809 | 1579 |
| LMArena Multi-Turn | 1513 | 1444 |
| EQ-Bench 4 | 1223 | — |
Frequently asked questions
Is Claude Opus 4.6 better than Kimi K2.5?
Claude Opus 4.6 is the stronger model overall, scoring 58.2 to 48.1 on the Noometry Index. Kimi K2.5 costs 11× less per token, which makes it the better buy when Claude Opus 4.6's lead doesn't matter for your workload.
Which is cheaper, Claude Opus 4.6 or Kimi K2.5?
Kimi K2.5 is cheaper. It lists at $0.45 per million input tokens and $2.25 per million output tokens; Claude Opus 4.6 lists at $5 and $25.
Is Claude Opus 4.6 or Kimi K2.5 better for coding?
Claude Opus 4.6 scores higher on coding benchmarks: 57.2 versus 48.8 in the Noometry coding category.
Which has the bigger context window?
Claude Opus 4.6 does, with 1M tokens against 262K.
How many benchmarks do Claude Opus 4.6 and Kimi K2.5 share?
47 benchmarks have published results for both models. Claude Opus 4.6 has 68 scored results on Noometry and Kimi K2.5 has 51.